Zobrazeno 1 - 10
of 2 305
pro vyhledávání: '"LIU Jialin"'
Large Language Models (LLMs) have made significant strides in the field of artificial intelligence, showcasing their ability to interact with humans and influence human cognition through information dissemination. However, recent studies have brought
Externí odkaz:
http://arxiv.org/abs/2411.14500
Most decentralized optimization algorithms are handcrafted. While endowed with strong theoretical guarantees, these algorithms generally target a broad class of problems, thereby not being adaptive or customized to specific problem features. This pap
Externí odkaz:
http://arxiv.org/abs/2410.01700
Fine-tuning large language models (LLMs) with Low-Rank adaption (LoRA) is widely acknowledged as an effective approach for continual learning for new tasks. However, it often suffers from catastrophic forgetting when dealing with multiple tasks seque
Externí odkaz:
http://arxiv.org/abs/2409.19611
Publikováno v:
IEEE Transactions on Evolutionary Computation (2014)
Multiobjective evolutionary learning (MOEL) has demonstrated its advantages of training fairer machine learning models considering a predefined set of conflicting objectives, including accuracy and different fairness measures. Recent works propose to
Externí odkaz:
http://arxiv.org/abs/2409.18499
Autor:
Wang, Xue, Zhou, Tian, Zhu, Jianqing, Liu, Jialin, Yuan, Kun, Yao, Tao, Yin, Wotao, Jin, Rong, Cai, HanQin
Attention based models have achieved many remarkable breakthroughs in numerous applications. However, the quadratic complexity of Attention makes the vanilla Attention based models hard to apply to long sequence tasks. Various improved Attention stru
Externí odkaz:
http://arxiv.org/abs/2408.08567
Autor:
Liu, Jialin, Liao, Diansheng
Constructing the new generation information processing system by mimicking biological nervous system is a feasible way for implement of high-efficient intelligent sensing device and bionic robot. However, most biological nervous system, especially th
Externí odkaz:
http://arxiv.org/abs/2408.05846
This paper presents an interactive platform to interpret multi-objective evolutionary algorithms. Sokoban level generation is selected as a showcase for its widespread use in procedural content generation. By balancing the emptiness and spatial diver
Externí odkaz:
http://arxiv.org/abs/2406.10663
Recently, procedural content generation has exhibited considerable advancements in the domain of 2D game level generation such as Super Mario Bros. and Sokoban through large language models (LLMs). To further validate the capabilities of LLMs, this p
Externí odkaz:
http://arxiv.org/abs/2406.08751
Quadratic programming (QP) is the most widely applied category of problems in nonlinear programming. Many applications require real-time/fast solutions, though not necessarily with high precision. Existing methods either involve matrix decomposition
Externí odkaz:
http://arxiv.org/abs/2406.05938
Learning to Optimize (L2O) stands at the intersection of traditional optimization and machine learning, utilizing the capabilities of machine learning to enhance conventional optimization techniques. As real-world optimization problems frequently sha
Externí odkaz:
http://arxiv.org/abs/2405.15251